European Pro League Cup 5 · BO3
result vs prediction
ALGO#146 in the world · win 2:0series probability
35%65%
probability at match start · final 2:0
EAC#76 in the world · loss 0:2The prediction was locked in using data as of the match start: map winrates, form and head-to-head were computed only from games before it began. This is how the model's honest accuracy is verified.
Map veto prediction
For each map — both teams' winrate over 3 months. The model guesses who bans it and who keeps it: teams remove maps where they are weaker and pull toward their strong ones.
AnubisEAC ban
44%50%
ALGO · 5 mapsedge EAC +6%EAC · 0 maps
NukeEAC ban
43%40%
ALGO · 3 mapsnearly even +3%EAC · 1 map
OverpassEAC pick
33%40%
ALGO · 2 mapsedge EAC +7%EAC · 1 map
InfernoALGO pick
50%50%
ALGO · 2 mapsnearly even +0%EAC · 0 maps
MirageALGO ban
33%50%
ALGO · 2 mapsedge EAC +17%EAC · 0 maps
DefaultALGO ban
40%50%
ALGO · 1 mapedge EAC +10%EAC · 0 maps
Most likely veto scenario
1. BanALGO remove Mirage
2. BanEAC remove Anubis
3. PickALGO take Inferno
4. PickEAC take Overpass
5. BanEAC remove Nuke
6. BanALGO remove Default
Prediction by map vs result
Probabilities were locked in using statistics as of the match start (map winrate over the 3 months before it). We compare against the actual result of each map.
Nukeprediction correct13:9
ALGO 56%EAC 44%
The model gave 56% on ALGO — the map was taken by ALGO.
Ancientprediction missed13:11
ALGO 47%EAC 53%
The model gave 53% on EAC — the map was taken by ALGO.
Model check result
Model favoriteEAC · 65%
Series resultALGO 2:0
Series predictionmissed
Accuracy by map1 of 2